© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16116
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the improvement or increase of something

    oai_token-act-pair · gemini-2.0-flash

    increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increase
    -0.69
    increasing
    -0.66
    increase
    -0.66
     Increase
    -0.65
     INCREASE
    -0.64
     Increasing
    -0.63
    INCRE
    -0.63
     increasing
    -0.63
    Increasing
    -0.63
     INCRE
    -0.62
    POSITIVE LOGITS
    
    0.64
     فريبيس
    0.58
     AppBundle
    0.54
    TypedDataSet
    0.52
     OnInit
    0.49
     typology
    0.49
     thyself
    0.48
    thentic
    0.47
    cagon
    0.47
     članak
    0.46
    Activations Density 10.032%

    No Known Activations